Forecasting first grade public school enrollment by neighborhood

Abstract The purpose of this study is to develop an alternative method to the traditional cohort survival technique for long-run forecasting of public school enrollment by small area. In the model presented, the difference between first grade enrollment and resident births lagged six years is viewed as a function of new housing, busing, and the percent of lagged births that are white. Least squares regression analysis was used to test the model on data in four neighborhoods in New York City for the period 1958–1969. While the model fits the historical data rather well, its usefulness for long-run forecasting is diminished in areas experiencing substantial structural change.